From: "Wangnan (F)" <wangnan0@huawei.com>
To: Arnaldo Carvalho de Melo <acme@redhat.com>, <ast@fb.com>
Cc: <lizefan@huawei.com>, <hekuang@huawei.com>,
Ingo Molnar <mingo@kernel.org>, <linux-kernel@vger.kernel.org>,
<pi3orama@163.com>, <joe@ovn.org>, Jiri Olsa <jolsa@kernel.org>,
<acme@kernel.org>
Subject: Re: [PATCH v3 10/30] perf clang: Add builtin clang support ant test case
Date: Mon, 5 Dec 2016 10:36:02 +0800 [thread overview]
Message-ID: <5844D292.3000506@huawei.com> (raw)
In-Reply-To: <20161202154440.GB5931@redhat.com>
On 2016/12/2 23:44, Arnaldo Carvalho de Melo wrote:
> Em Sat, Nov 26, 2016 at 07:03:34AM +0000, Wang Nan escreveu:
>> Add basic clang support in clang.cpp and test__clang() testcase. The
>> first testcase checks if builtin clang is able to generate LLVM IR.
>>
>> tests/clang.c is a proxy. Real testcase resides in
>> utils/c++/clang-test.cpp in c++ and exports C interface to perf test
>> subsystem.
>>
>> Test result:
>>
>> $ perf test -v clang
>> 51: Test builtin clang support :
>> 51.1: Test builtin clang compile C source to IR :
>> --- start ---
>> test child forked, pid 13215
>> test child finished with 0
>> ---- end ----
>> Test builtin clang support subtest 0: Ok
> While testing this I noticed that the perf binary got huge, can't this
> be done in some other way, i.e. using dynamic library?
I intentionally use statically linking because it is good for
smartphone: we can simply 'adb push' a statically linked perf
to Android.
The resulting ELF executable would be even larger if LLVM is
built with default setting.
In my setting the resuling 'perf' is less than 60MB:
$ ls -s ~/perf -h
58M /home/wn/perf
$ size ~/perf
text data bss dec hex filename
56931273 2950808 24108632 83990713 50198b9 /home/wn/perf
It is reasonable for me.
I think using dynamic clang and llvm libraries is possible but I
never tried it before. It depend on LLVM compiling. I think if
distro provides shared libraries then perf can utilize them
automatically. Let me check it today.
About the file size, I discussed with Alexei, he taught me a lot
on it. Maybe he or his ioVisor ex-colleagues can provide some
new idea?
Thank you.
next prev parent reply other threads:[~2016-12-05 2:37 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-11-26 7:03 [PATCH v3 00/30] perf clang: Builtin clang and perfhook support Wang Nan
2016-11-26 7:03 ` [PATCH v3 01/30] tools lib bpf: Add missing BPF functions Wang Nan
2016-11-26 17:10 ` Alexei Starovoitov
2016-12-02 10:37 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 02/30] tools lib bpf: Add private field for bpf_object Wang Nan
2016-11-26 17:11 ` Alexei Starovoitov
2016-12-02 10:37 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 03/30] tools lib bpf: Retrive bpf_map through offset of bpf_map_def Wang Nan
2016-11-26 17:12 ` Alexei Starovoitov
2016-12-02 10:38 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 04/30] perf tools: Introduce perf hooks Wang Nan
2016-12-02 10:38 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 05/30] perf tools: Pass context to perf hook functions Wang Nan
2016-12-06 8:21 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 06/30] perf llvm: Extract helpers in llvm-utils.c Wang Nan
2016-12-06 8:21 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 07/30] tools build: Add feature detection for LLVM Wang Nan
2016-12-06 8:22 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 08/30] tools build: Add feature detection for clang Wang Nan
2016-12-06 8:22 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 09/30] perf build: Add clang and llvm compile and linking support Wang Nan
2016-12-06 8:23 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 10/30] perf clang: Add builtin clang support ant test case Wang Nan
2016-11-26 17:17 ` Alexei Starovoitov
2016-11-28 7:41 ` Wangnan (F)
2016-12-02 15:44 ` Arnaldo Carvalho de Melo
2016-12-05 2:36 ` Wangnan (F) [this message]
2016-12-05 4:41 ` Wangnan (F)
2017-01-17 13:38 ` Arnaldo Carvalho de Melo
2016-12-05 16:51 ` Alexei Starovoitov
2016-12-05 21:02 ` Arnaldo Carvalho de Melo
2016-12-05 21:48 ` Arnaldo Carvalho de Melo
2016-12-06 2:07 ` Wangnan (F)
2016-12-06 13:43 ` Arnaldo Carvalho de Melo
2016-12-06 19:19 ` Arnaldo Carvalho de Melo
2016-12-06 21:02 ` Arnaldo Carvalho de Melo
2016-12-06 8:23 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 11/30] perf clang: Use real file system for #include Wang Nan
2016-12-06 8:24 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 12/30] perf clang: Allow passing CFLAGS to builtin clang Wang Nan
2016-12-06 8:25 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 13/30] perf clang: Update test case to use real BPF script Wang Nan
2016-12-06 8:25 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 14/30] perf clang: Support compile IR to BPF object and add testcase Wang Nan
2016-11-26 17:25 ` Alexei Starovoitov
2016-11-28 6:32 ` Wangnan (F)
2016-11-28 10:31 ` Wangnan (F)
2016-11-28 19:33 ` Alexei Starovoitov
2016-12-06 8:26 ` [tip:perf/core] " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 15/30] perf clang: Compile BPF script use builtin clang support Wang Nan
2016-12-06 8:26 ` [tip:perf/core] perf clang: Compile BPF script using " tip-bot for Wang Nan
2016-11-26 7:03 ` [PATCH v3 16/30] perf clang: Pass full path to builtin clang Wang Nan
2016-11-26 7:03 ` [PATCH v3 17/30] perf clang: Pass CFLAGS " Wang Nan
2016-11-26 7:03 ` [PATCH v3 18/30] perf clang jit: Wrap llvm::Module using PerfModule Wang Nan
2016-11-26 7:03 ` [PATCH v3 19/30] perf clang jit: Insignt BPF and JIT functions in a Module Wang Nan
2016-11-26 17:32 ` Alexei Starovoitov
2016-11-26 7:03 ` [PATCH v3 20/30] perf clang jit: add PerfModule::doJIT to JIT perfhook functions Wang Nan
2016-11-26 17:29 ` Alexei Starovoitov
2016-11-28 6:42 ` Wangnan (F)
2016-11-26 7:03 ` [PATCH v3 21/30] perf clang jit: Export functions for jitted code Wang Nan
2016-11-26 7:03 ` [PATCH v3 22/30] perf clang jit: Actually JIT and hook in bpf loader Wang Nan
2016-11-26 7:03 ` [PATCH v3 23/30] perf clang jit: Collect the lowest address in maps section as map_base Wang Nan
2016-11-26 7:03 ` [PATCH v3 24/30] perf clang jit: Retrive fd of BPF map from its offset Wang Nan
2016-11-26 7:03 ` [PATCH v3 25/30] perf clang jit: Allow jitted perf hook access BPF maps Wang Nan
2016-11-26 17:09 ` Alexei Starovoitov
2016-11-26 7:03 ` [PATCH v3 26/30] perf clang: Link BPF functions declaration into perf Wang Nan
2016-11-26 17:40 ` Alexei Starovoitov
2016-11-30 16:12 ` Arnaldo Carvalho de Melo
2016-12-01 1:56 ` [PATCH v3 26/30 - cleanup] " Wang Nan
2016-11-26 7:03 ` [PATCH v3 27/30] perf clang: Declare BPF functions for BPF scripts automatically Wang Nan
2016-11-26 7:03 ` [PATCH v3 28/30] perf clang: Include helpers to BPF scripts Wang Nan
2016-11-26 7:03 ` [PATCH v3 29/30] perf clang builtin: Define hook helpers by default Wang Nan
2016-11-26 7:03 ` [PATCH v3 30/30] perf clang jit: Export getpid() to perf hook Wang Nan
2016-12-07 1:57 [PATCH v3 10/30] perf clang: Add builtin clang support ant test case Alexei Starovoitov
2017-01-17 18:27 Alexei Starovoitov
2017-01-17 19:04 ` Arnaldo Carvalho de Melo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=5844D292.3000506@huawei.com \
--to=wangnan0@huawei.com \
--cc=acme@kernel.org \
--cc=acme@redhat.com \
--cc=ast@fb.com \
--cc=hekuang@huawei.com \
--cc=joe@ovn.org \
--cc=jolsa@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lizefan@huawei.com \
--cc=mingo@kernel.org \
--cc=pi3orama@163.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome